In [1]:
#### Importing Libraries ####
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sn
In [2]:
dataset = pd.read_csv('financial_data.csv')
In [3]:
dataset.head()
Out[3]:
In [4]:
dataset.columns
Out[4]:
In [5]:
dataset.describe()
Out[5]:
In [6]:
dataset.isnull().any()
Out[6]:
In [7]:
dataset2 = dataset.drop(['entry_id', 'pay_schedule', 'e_signed'], axis = 1)
In [9]:
# paiwise scatter plot
plt.figure(figsize=(20, 10))
sn.pairplot(dataset2)
plt.show()
In [43]:
sn.distplot(dataset['income'])
plt.show()
In [44]:
sn.distplot(dataset['amount_requested'])
plt.show()
In [45]:
sn.distplot(dataset['risk_score'])
plt.show()
In [46]:
sn.distplot(dataset['inquiries_last_month'])
plt.show()
In [10]:
dataset2.corrwith(dataset.e_signed).plot.bar(figsize = (18, 15),
title= 'Correlation with Esigned', fontsize = 15,
rot = 45, grid = True)
Out[10]:
In [11]:
## Correlation Matrix
sn.set(style="white")
# Compute the correlation matrix
corr = dataset2.corr()
# Generate a mask for the upper triangle
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
# Set up the matplotlib figure
f, ax = plt.subplots(figsize=(22, 20))
# Generate a custom diverging colormap
cmap = sn.diverging_palette(220, 10, as_cmap=True)
# Draw the heatmap with the mask and correct aspect ratio
sn.heatmap(corr, mask=mask, cmap=cmap, vmax=.3, center=0,
square=True, linewidths=.5, cbar_kws={"shrink": .5})
Out[11]:
In [12]:
# Feature Engineering
dataset = dataset.drop(['months_employed'], axis = 1)
In [13]:
dataset['personal_account_months'] = (dataset.personal_account_m + (dataset.personal_account_y * 12))
In [14]:
dataset[['personal_account_m', 'personal_account_y', 'personal_account_months']].head()
Out[14]:
In [15]:
dataset = dataset.drop(['personal_account_m', 'personal_account_y'],axis = 1)
In [16]:
# One Hot Encoding
dataset = pd.get_dummies(dataset)
In [17]:
dataset.columns
Out[17]:
In [18]:
dataset = dataset.drop(['pay_schedule_semi-monthly'], axis = 1)
In [19]:
# Removing extra columns
response = dataset["e_signed"]
users = dataset['entry_id']
dataset = dataset.drop(["e_signed", "entry_id"], axis =1)
In [21]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(dataset, response, test_size = 0.2, random_state = 0)
In [22]:
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train2 = pd.DataFrame(sc_X.fit_transform(X_train))
X_test2 = pd.DataFrame(sc_X.fit_transform(X_test))
X_train2.columns = X_train.columns.values
X_test2.columns = X_test.columns.values
X_train2.index = X_train.index.values
X_test.index = X_test.index.values
X_train = X_train2
X_test = X_test2
In [23]:
#### Model Building ####
### Comparing Models
## Logistic Regression
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0, penalty = 'l1')
classifier.fit(X_train, y_train)
Out[23]:
In [24]:
# Predicting Test Set
y_pred = classifier.predict(X_test)
from sklearn.metrics import confusion_matrix, accuracy_score, f1_score, precision_score, recall_score
acc = accuracy_score(y_test, y_pred)
prec = precision_score(y_test, y_pred)
rec = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
In [25]:
results = pd.DataFrame([['LogisticRegression acc', acc, prec, rec, f1]],
columns = ['Model', 'Accuracy', 'Precision', 'Recall', 'F1 Score'])
print(results)
In [26]:
## SVM (Linear)
from sklearn.svm import SVC
classifier = SVC(random_state = 0, kernel = 'linear')
classifier.fit(X_train, y_train)
Out[26]:
In [27]:
# Predicting Test Set
y_pred = classifier.predict(X_test)
acc = accuracy_score(y_test, y_pred)
prec = precision_score(y_test, y_pred)
rec = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
In [28]:
model_results = pd.DataFrame([['SVM (Linear)', acc, prec, rec, f1]],
columns = ['Model', 'Accuracy', 'Precision', 'Recall', 'F1 Score'])
In [29]:
results = results.append(model_results, ignore_index = True)
In [30]:
## SVM (rbf)
from sklearn.svm import SVC
classifier = SVC(random_state = 0, kernel = 'rbf')
classifier.fit(X_train, y_train)
Out[30]:
In [31]:
# Predicting Test Set
y_pred = classifier.predict(X_test)
acc = accuracy_score(y_test, y_pred)
prec = precision_score(y_test, y_pred)
rec = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
In [32]:
model_results = pd.DataFrame([['SVM (RBF)', acc, prec, rec, f1]],
columns = ['Model', 'Accuracy', 'Precision', 'Recall', 'F1 Score'])
In [33]:
results = results.append(model_results, ignore_index = True)
In [34]:
## random forest classifier
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(random_state = 0, n_estimators = 100,
criterion = 'entropy')
classifier.fit(X_train, y_train)
Out[34]:
In [35]:
# Predicting Test Set
y_pred = classifier.predict(X_test)
acc = accuracy_score(y_test, y_pred)
prec = precision_score(y_test, y_pred)
rec = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
In [36]:
model_results = pd.DataFrame([['Random Forest (n=100)', acc, prec, rec, f1]],
columns = ['Model', 'Accuracy', 'Precision', 'Recall', 'F1 Score'])
In [37]:
results = results.append(model_results, ignore_index = True)
In [39]:
## K-fold Cross Validation
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X= X_train, y = y_train,
cv = 10)
In [40]:
print("Random Forest Classifier Accuracy: %0.2f (+/- %0.2f)" % (accuracies.mean(), accuracies.std() * 2))
In [49]:
results = results.append(model_results, ignore_index = True)
In [51]:
results
Out[51]:
In [ ]: